Gemini 3.1 Pro API Pricing
Short answer
Gemini 3.1 Pro costs $2.00 per 1M input tokens and $12.00 per 1M output tokens (cached input $0.20/1M). Context window: 1,048,576. Last verified 2026-06-17 from ai.google.dev. Confidence: Verified.
Gemini 3.1 Pro is Google's flagship reasoning model (preview, paid-only) with full multimodal input and a 1M context window.
Input
$2.00 /1M
Output
$12.00 /1M
Cached input
$0.20 /1M
Input pricing$2.00
Cached input$0.20
Output pricing$12.00
Limits & capabilities
Context window1,048,576
Max output65,536
Modalitytext/image/video/audio/PDF input, text output
ChannelGemini Developer API
ProviderGoogle Gemini
Best for
ReasoningAgenticLong context
Prompts over 200K bill $4 input / $18 output. Thinking tokens billed as output. Vertex non-global endpoints add ~10% from Jul 1 2026.
Last checked Verified
More from Google Gemini
Gemini 3.5 Flash
$1.50 /1M in
$9.00 /1M out
Coding, Agentic, Fast
Gemini 3.1 Flash-Lite
$0.25 /1M in
$1.50 /1M out
Low cost, High volume, Fast
Gemini 2.5 Pro
$1.25 /1M in
$10.00 /1M out
Reasoning, Long context, Multimodal
Gemini 2.5 Flash
$0.30 /1M in
$2.50 /1M out
Low latency, High volume, Multimodal
Gemini 2.5 Flash-Lite
$0.10 /1M in
$0.40 /1M out
Lowest cost, High volume
Imagen 4
— /1M in
— /1M out
Photoreal, Text-to-image, Bulk